Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    television

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     od
    -0.07
     mile
    -0.07
     mật
    -0.07
    cwd
    -0.07
    .refresh
    -0.07
    >Contact
    -0.06
     refinement
    -0.06
     upd
    -0.06
     FAST
    -0.06
    ountain
    -0.06
    POSITIVE LOGITS
    []
↵
    0.06
     yayım
    0.06
     Kre
    0.06
    .stem
    0.06
    大学
    0.06
     Garcia
    0.06
    担当
    0.06
    unkt
    0.06
     aspir
    0.06
    овари
    0.06
    Act Density 0.004%

    No Known Activations